A two-stage energy management and optimal control for hybrid AC/DC microgrids using neural fuzzy logic and nonlinear sliding mode control
Muhammad Zubair Bhayo, Yang Han, Kalsoom Bhagat, Mohsin Ali Tunio, Fazal Hussain
Abstract
This study presents a two-stage energy management and control framework for hybrid AC/DC microgrids integrating wind and solar energy sources alongside lithium-ion battery storage. In the first stage, renewable energy extraction is enhanced using a nonlinear auto-regressive moving average–based controller, developed to maximize the power output from photovoltaic arrays and wind turbines. The second stage addresses system stability and load balancing through a hybrid control scheme that combines neural fuzzy logic controller with nonlinear sliding mode control. This hierarchical strategy is designed to maintain DC bus voltage and regulate AC frequency under variable load and generation conditions. The proposed architecture enables coordinated operation of distributed energy resources, thereby improving voltage–frequency stability, enhancing system adaptability, and increasing energy utilization efficiency. Overall, the proposed framework enables reliable integration of renewable energy sources into contemporary microgrid architectures, thereby enhancing system resilience and supporting sustainable energy delivery.